INDEX

Explanations

verbs that indicate actions or processes related to meetings, discussions, development, and problem-solving

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ox

-0.18

their

-0.18

eb

-0.17

ov

-0.17

Ñı

-0.17

och

-0.17

um

-0.16

oth

-0.16

Ñķ

-0.16

those

-0.16

POSITIVE LOGITS

cales

0.19

 itself

0.19

/is

0.16

heets

0.15

pr

0.15

dz

0.15

urette

0.15

dong

0.14

nt

0.14

uars

0.14

Activations Density 0.792%

verbs that indicate actions or processes related to meetings, discussions, development, and problem-solving

No Comments

No Known Activations